HotStack

← Back to browse

agentic-research

Indexed by io.github.TheAiSingularity
View source ↗

About

Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.

Use this server

Add it to your MCP client. The catalogue lists this config verbatim from its source — it does not run, download, or vouch for the server. Review the command before you run it.

Transportstdio (runs a local command)
Env varsOPENAI_BASE_URL OPENAI_API_KEY MODEL_SYNTHESIZER MODEL_PLANNER EMBED_MODEL SEARXNG_URL LOCAL_CORPUS_PATH ENABLE_RERANK ENABLE_FETCH
Claude Code 
claude mcp add --env OPENAI_BASE_URL= --env OPENAI_API_KEY= --env MODEL_SYNTHESIZER= --env MODEL_PLANNER= --env EMBED_MODEL= --env SEARXNG_URL= --env LOCAL_CORPUS_PATH= --env ENABLE_RERANK= --env ENABLE_FETCH= agentic-research -- uvx agentic-research-engine
Cursor

Add to Cursor

If the button doesn't open Cursor, use the JSON below — Cursor accepts the same mcpServers config.

VS Code 
code --add-mcp '{"name":"agentic-research","command":"uvx","args":["agentic-research-engine"],"env":{"OPENAI_BASE_URL":"","OPENAI_API_KEY":"","MODEL_SYNTHESIZER":"","MODEL_PLANNER":"","EMBED_MODEL":"","SEARXNG_URL":"","LOCAL_CORPUS_PATH":"","ENABLE_RERANK":"","ENABLE_FETCH":""}}'
JSON 
{
  "mcpServers": {
    "agentic-research": {
      "command": "uvx",
      "args": [
        "agentic-research-engine"
      ],
      "env": {
        "OPENAI_BASE_URL": "",
        "OPENAI_API_KEY": "",
        "MODEL_SYNTHESIZER": "",
        "MODEL_PLANNER": "",
        "EMBED_MODEL": "",
        "SEARXNG_URL": "",
        "LOCAL_CORPUS_PATH": "",
        "ENABLE_RERANK": "",
        "ENABLE_FETCH": ""
      }
    }
  }
}

Environment variables are listed by name only — fill in your own values. Entries never carry secrets.